Paper Info
Title
Deep Sequential Models for Suicidal Ideation from Multiple Source Data.
Abstract
This paper presents a novel method for predicting suicidal ideation from electronic health records (EHR) and ecological momentary assessment (EMA) data using deep sequential models. Both EHR longitudinal data and EMA question forms are defined by asynchronous, variable length, randomly sampled data sequences. In our method, we model each of them with a recurrent neural network, and both sequences are aligned by concatenating the hidden state of each of them using temporal marks. Furthermore, we incorporate attention schemes to improve performance in long sequences and time-independent pre-trained schemes to cope with very short sequences. Using a database of 1023 patients, our experimental results show that the addition of EMA records boosts the system recall to predict the suicidal ideation diagnosis from 48.13 obtained exclusively from EHR-based state-of-the-art methods to 67.78. Additionally, our method provides interpretability through the t-distributed stochastic neighbor embedding (t-SNE) representation of the latent space. Furthermore, the most relevant input features are identified and interpreted medically.
Year
DOI
Venue
2019
10.1109/JBHI.2019.2919270
IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS
Keywords
Field
DocType
Predictive models,Data models,Recurrent neural networks,Psychiatry,Informatics,Biological system modeling,Databases,Deep learning,RNN,attention,EMA,suicide
Data mining,Interpretability,Data modeling,Asynchronous communication,Pattern recognition,Computer science,Source data,Recurrent neural network,Suicidal ideation,Artificial intelligence,Concatenation,Recall
Journal
Volume
Issue
ISSN
23
6
2168-2194
Citations 
PageRank 
References 
0
0.34
0
Authors
7
Name
Order
Citations
PageRank
Ignacio Peis100.68
Pablo M. Olmos211418.97
Constanza Vera-Varela300.34
María Luisa Barrigón400.68
Philippe Courtet511.07
Enrique Baca-Garcia6124.80
Antonio Artés-Rodríguez720634.76